No label defined (Q3677010)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3898069
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3898069 |
Statements
1984
0 references
characteristic polynomial
0 references
best linear prediction
0 references
autoregressive time series
0 references
incomplete information
0 references
moving average process
0 references
mean square error of prediction
0 references
0.8456498384475708
0 references
0.8267548084259033
0 references
A method to find the best linear prediction of q-th order autoregressive time series having incomplete information is derived. If \(\{Y_ t\}\) is a q-th order autoregressive time series which can be represented as a moving average process, \(E(Y_ t)=0\), the autocovariation function of the series and the realization of the time series \(\{Y_ tX_ t\}\) are known, \(\{X_ t\}\) being a stationary time series independent of \(\{Y_ t\}\), under some natural conditions the best linear prediction of \(\{Y_ t\}\) is derived from a system of algebraic linear equations. The case of the first order autoregressive time series with zero mean is also exposed. The mean square error of prediction is given. The author states the existence of an analogous result for the prediction of a finite moving average process.
0 references